Overcoming catastrophic forgetting by incremental moment matching

SW Lee, JH Kim, J Jun, JW Ha… - Advances in neural …, 2017 - proceedings.neurips.cc
Catastrophic forgetting is a problem of neural networks that loses the information of the first
task after training the second task. Here, we propose a method, ie incremental moment …

A review of methodologies for integrating human factors and ergonomics in engineering design

X Sun, R Houssin, J Renaud… - International Journal of …, 2019 - Taylor & Francis
The requirements of Human Factors and Ergonomics (HF/E) in engineering design must be
satisfied, including usability, safety, reliability, and operability in the workplace and work …

Catastrophic forgetting in deep learning: A comprehensive taxonomy

EL Aleixo, JG Colonna, M Cristo… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep Learning models have achieved remarkable performance in tasks such as image
classification or generation, often surpassing human accuracy. However, they can struggle …

Smart textiles for improved quality of life and cognitive assessment

G Oatley, T Choudhury, P Buckman - Sensors, 2021 - mdpi.com
Smart textiles can be used as innovative solutions to amuse, meaningfully engage, comfort,
entertain, stimulate, and to overall improve the quality of life for people living in care homes …

[PDF][PDF] 深度记忆网络研究进展

刘建伟, 王园方, 罗雄麟 - 计算机学报, 2020 - 159.226.43.17
摘要近年来, 随着深度神经网络的快速发展, 它在越来越多的领域中有了广泛的应用.
深度神经网络模型在处理有序列依赖关系的预测问题时, 需要利用之前学习到的信息进行记忆 …

Context recognition and ubiquitous computing in smart cities: a systematic mapping

LV do Nascimento, GM Machado, V Maran… - Computing, 2021 - Springer
Smart cities are one of the emerging domains for computational applications. Many of these
applications may benefit from the ubiquitous computing paradigm to provide better services …

The relationship between stress levels measured by a questionnaire and the data obtained by smart glasses and finger pulse oximeters among polish dental students

K Mocny-Pachońska, RJ Doniec, S Sieciński… - Applied Sciences, 2021 - mdpi.com
Stress is a physical, mental, or emotional response to a change and is a significant problem
in modern society. In addition to questionnaires, levels of stress may be assessed by …

Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy

EL Aleixo, JG Colonna, M Cristo… - Journal of the …, 2024 - journals-sol.sbc.org.br
Deep Learning models have achieved remarkable performance in tasks such as image
classification or generation, often surpassing human accuracy. However, they can struggle …

[PDF][PDF] Diagnostic classification and symbolic guidance to understand and improve recurrent neural networks

D Hupkes, W Zuidema - Interpreting, explaining and visualizing …, 2017 - projects.illc.uva.nl
This paper describes a search through a variety of methods to inspect and understand the
internal dynamics of gated recurrent neural networks, using a task focusing on a key feature …

[PDF][PDF] 인간지능과기계지능-인지주의인공지능

BT Jang - Communications of the Korean Institute of Information …, 2018 - koreascience.kr
1950 년대에 컴퓨터의 등장과 함께 탄생한 인공지능 (Artificial Intelligence, Al) 3-X| ł 60o. 59 h
5-ZHZļ9] 큰 파러다임을 탐구하였다. 초기 30 년 동안 (1960-1990) 의 제 1 기 기호주의 …